AI News, BOOK REVIEW: Google AI system beats doctors in detection tests for breast cancer ... artificial intelligence

Google AI Can Now Detect Breast Cancer Better Than Doctors

The advent of artificial intelligence (AI) has brought a host of technologies that make everyday tasks easier.

The most widely used examples include providing more relevant internet searches, predicting the next word in a text message, identifying the face in a photo on social media, and routing commuters around trouble spots in traffic.

A study published in the scientific journal Nature showed that Google's AI system could detect breast cancer in mammograms more accurately than human radiologists.  This breakthrough could lead to better screening tools for those that don't yet have any signs of the disease.

Imperial Centre, Northwestern University, and Royal Surrey County Hospital to determine if a properly trained AI system could 'spot the signs of breast cancer more accurately.'  The researchers trained the AI system using mammograms from 15,000 women in the U.S. and 76,000 women in the United Kingdom (U.K.).

Research shows that half of all women who get a mammogram yearly will get at least one false positive over a 10-year period.  Detecting cancerous tissue in mammograms is particularly tricky because tumors are difficult to spot in the dense and overlapping tissue found in the breast.

In that study, the GoogLeNet AI system studied thousands of mammograms supplied by a Dutch university and identified malignant tumors with an 89% accuracy rate, compared to just 73% achieved by human pathologists.  The latest research takes the system to the next level, not only by detecting cancer but also by reducing the frequency of incorrect diagnoses.

Google AI Can Now Detect Breast Cancer Better Than Doctors

The advent of artificial intelligence (AI) has brought a host of technologies that make everyday tasks easier.

The most widely used examples include providing more relevant internet searches, predicting the next word in a text message, identifying the face in a photo on social media, and routing commuters around trouble spots in traffic.

A study published in the scientific journal Nature showed that Google's AI system could detect breast cancer in mammograms more accurately than human radiologists.  This breakthrough could lead to better screening tools for those that don't yet have any signs of the disease.

Imperial Centre, Northwestern University, and Royal Surrey County Hospital to determine if a properly trained AI system could 'spot the signs of breast cancer more accurately.'  The researchers trained the AI system using mammograms from 15,000 women in the U.S. and 76,000 women in the United Kingdom (U.K.).

Once the algorithms had been trained to detect breast cancer, they were tasked with searching for cancerous cells in mammograms of women who were already proven to have the disease, as a way to test the accuracy of the algorithm.

Research shows that half of all women who get a mammogram yearly will get at least one false positive over a 10-year period.  Detecting cancerous tissue in mammograms is particularly tricky because tumors are difficult to spot in the dense and overlapping tissue found in the breast.

In that study, the GoogLeNet AI system studied thousands of mammograms supplied by a Dutch university and identified malignant tumors with an 89% accuracy rate, compared to just 73% achieved by human pathologists.  The latest research takes the system to the next level, not only by detecting cancer but also by reducing the frequency of incorrect diagnoses.

New Concept and New Way of Treatment of Cancer

In 1985, the author made follow-up survey to over 3000 patients who had experienced general surgical and chest cancer operations performed by the author, and found that most the patients experienced recurrence and metastasis within 2 to 3 years after the operation or even within several months for some patients, from which I deeply realized that the operation was successful and standard, but the long-term effective was unsatisfactory or even unsuccessful.

Since 1970s, in view of the extremely high recurrence and metastasis rate after operation, to prevent the recurrence and metastasis after operation, a series of assistant chemotherapy has been adopted after operation or even before operation (such as mastocarcinoma), but the results have been not satisfactory.

I have observed from a great many of patients in our tumor special clinic that assistant chemotherapy after operation fails to prevent recurrence and metastasis and intensive recurrence and metastasis causes the failure of immunologic function to some cases.

Many basic concepts and theories are still not clear and the curative effect is not high, therefore, we must make clinical fundamental research in depth and it will be difficult to improve the clinical curative effect in case of no breakthrough in fundamental clinical research.

The classical tumor mode concept was established based on the understanding of integrated level of cytology, pathology, cell biology, microbiology and anatomy and cellular level in the end of 19th century and the first half 20th century.

They held that tumor originated from individual cell, that is to say, tumor was originated from clone, cancer cells were able to regenerate autonomously and were divided and reproduced continuously, one to two and two to four, therefore, cancer cells were the arch criminal and the root of canceration, and they must be killed.

after the middle period of 20th Century, the range of tumor surgical operation became larger due to the progress in the technology of surgical operation, a series of super radical operations, such as expanded radical mastectomy.

It was proved by the practice over years that the expanded surgical removal range could not improve the tumor-free survival time and total survival time for most cancerous protuberances, such as lung cancer, liver cancer and cancer of pancreas.

It was proved by facts that radium was quite effective to massive tumor, any tumor would shrink rapidly after injection with syringe needle painted with radium on the tip, and the radium therapy was the main method for cancer treatment for decades of years.

After the Second World War (1946), it is found that the cell toxicant (Nitrogen mustard) and its derivation in the chemical warfare have obvious inhibitory action on tumor, however, due to its poor selectivity, it is called cytotoxic drug, it can kill cancer cells and kill the normal cells of host at the same time, so the toxic side effect is relatively large.

However, up to the beginning of 21st Century, cancer is still very rampant, the incidence rate of cancer grows continuously, the death rate is still quite high, and the recurrence and metastasis still cannot be prevented, even though many patients receive normal and systematic radiotherapy and chemotherapy after operation.

(III) Concept of traditional cancer therapeutics It is held by the traditional concept that cancinoma is the continual division and proliferation of cancer cells, so the treatment must target killing the cancer cells, so these three goals of traditional cancer therapeutics are determined based on the concept of traditional mode of killing off the cancer cells.

Subsequently, it has been proven by the practice for years that the expansion of extent of surgical removal of the cancer cells, such as breast cancer, lung cancer, liver cancer and pancreatic cancer, has not improved the cancer-free survival time and total survival time.

To sum up, the concept of traditional cancer therapeutics holds the tumor is based on the maniac division and proliferation of the cells, so the cancer cells are the arch criminal, as a result, the target of the treatment goal of the traditional cancer therapeutics is the cancer cell, namely killing-off of the cancer cells.

(I) Assumptive new mode of cancer therapeutics The assumptive new mode of cancer therapeutics includes some new examples and its predominant idea holds that cancer is a kind of disease, the regulation and signal transmission among the cells are disrupted instead of loss and the carcinogenesis is a continuous entity with possibility of reversion.

When people increase the concentration and dosage of the chemotherapeutic drugs to make them more aggressive to the cancer cells (such as intensified radiotherapy), we right lead the mechanism of long-term survival or healing to the more dangerous way, even bring about the artificial or iatrogenic immunologic function breakdown.

However, the metabolism of most of the cells has the capacity of keeping balance, in addition, in order to heal the patient suffering from the tumor, it is not required that the canceration meet with the reversion in all directions, it is only necessary to regulate the key steps such as proliferation, infiltration and metastasis of cancer cells again or make the key steps reversed.

Shanghai Tumor Research Institute had extracted RNA from the normal hepatic cells, then incubated and cultivated it together with the liver cancer cells to correct the abnormal genetic activities of the liver cancer cells through the regulation and control reaction of normal liver RNA so as to make it reversed to the normal cells.

The work to induce the cells to differentiate to the normal cells to reverse the tumor cells is just remaining in the early stage, no matter the rule of regulating and controlling the cell differentiation with nucleic acid or the rule of regulating and controlling the cell differentiation with drugs, is not made clear and it needs further study.

Some scientists hold that it is possible to realize the reversion of the tumor in the early stage of the canceration while the tumor becomes an irreversible canceration in the late stage of the cancer, therefore, they put forward a suggestion: it is not necessary to induce the tumor to return to the normal state, but it is necessary to induce the tumor to differentiate to mature or make for apoptosis and death.

Killing tumor cells: the precondition of adopting the cytotoxic drugs to treat the tumor is the understanding that the it is not only possible but also necessary to kill the last cancer cell until it is proven by the clinic application and the lab that the tumor has been entirely eliminated, as is the prerequisite of healing the patient suffering from the tumor.

In the recent 16 years, among 12000 patients suffering from metaphase and advanced cancer treated by Shuguang Tumor Research Institute and Wuchang Shuguang Tumor Special Clinic, some reoccurrence and metastasis patients, such as the patients with anastomotic stoma reoccurrence cancer and gastric carcinoma that cannot be ablated or treated through radiotherapy and chemotherapy, after taking Z-C medicine for a long time over 3-5 years, the conditions are controlled and stabilized, they can survive with tumor (coexist with the tumor) and take care of themselves, the survival quality is good and the survival quality is obviously prolonged.

It is deemed by us that undoubtedly we should kill the foreigners invading the body, however, as to the cancer cells, we shall make a differential treatment just because they are only the variant tissues in the normal body of the host, here we reaffirm that the cancer shall be treated through regulating the control over them by the mechanism instead of the necessary and impossible killing-off of all cancer cells.

In view of the experience and lessons of the author over half a century, now we should research the urgent problems in the current cancer study, seek for the breakthrough for clinical research from the weak link of the modern medicine and find the breakthrough of prevention and control from the invasion, reoccurrence and metastasis, look for the anti-reoccurrence and anti-metastasis drugs from the chemical drugs and the natural herbs and deepen the new understanding of the cancer concept at the molecular level, genetic level, integrated treatment level and targeted treatment.

1950s, an unexpected experiment result was found that when a toxic diplococcus pneumoniae, killed at high temperature, was mixed with a nontoxic diplococcus pneumoniae and injected into the body of a mouse, the mouse would die of disease, and toxic diplococcus pneumoniae could be separated out of the dead mouse.

Since mid-1970s, with the new progress of life science, establishment and development of DNA recombination, gene transfer and hydridoma technology, genetic engineering, protein engineering technology, it is possible to study the nature and characteristics of cancer cells by a combination of molecular level and cellular level, and find out anti-cancer approaches and reverse and differentiation or cancer gene treatments.

Whether for growth factor, hormone or oncogene products, apoptosis, their effects of promoting cell proliferation and inducing cell death come down to affecting operation of the cell cycle, which is under the control of cell cyclin dependent kinase and its inhibitors.

To ensure relative stability of its own genetic information, eliminate harmful mutation of DNA molecule, kill cancer cells in the body, human body has a whole set of immune defense system, which will give out alarm signals in case of occurrence of abnormal cells.

In 1980s, the scientists separated out an alarm signal of malignant tumor, referred to as recognition factor, which was a kind of protein, gave out alarm, announced the occurrence of cancer cells in the body and summoned leukocyte responsible for cleaning to attack cancer cells.

In 1985 while the author was conducting the experimental study of modeling of animal inoculated with tumor cells, he made over 400 modeling experiments, which all failed, and later ablated the mice’s thymus first, leading to complete success in modeling.

There have been two views of cancer occurrence and evolution: One view is that cancer occurrence and evolution is an independent process basically unrestricted by any defense mechanism, treatment should focus on tumor itself while paying little attention to regulating effects of immune system of the organism.

The other view is that cancer occurrence and evolution is a dependent process or controlled process regulated by multiple factors within the body, especially immune factors, which entails that treatment should pay equal attention to eliminating the pathogenic factors and reinforcing the vital qi.

Until now, tumor biology has developed to the level of molecular biology, cytokine and gene, while the theoretical basis of tumor therapeutics remains at the cytology level half a century ago, which is constant proliferation of cancer cells aimed at killing cancer cells.

The traditional idea and work method based on cell toxicant is under attack, research scope of anti-tumor drugs has not been limited to traditional cell toxicant drug, differentiation inducer and biological reaction moderator, immunologic regulatory Chinese medicines combining Chinese and western medicine are emerging.

Immunological therapy: as the clinic evidence related with immunity and immune index such as spontaneous extinction of individual tumor indicate that immunologic function of the organism is declining with the evolution of tumor, enlightening us to expect much of immunologic therapy of tumor.

The use of cell engineering technology can produce large quantities of cell toxicant active cells such as macrophages, cell toxicant T lymphocyte, killer cell capable of naturally killing cells and lymphokine activation, as well as hybridoma cell excreting monoclone antibody.

The difference does not lie in that it does not kill tumor cells, but that it induces the tumor cells to differentiate towards mature phase under the effect of differentiated inducement agent, recover the normal or approximately normal representation and functions of the cell.

Biological therapy: One of the major achievements in life science and medical science in 1980s is the rapid emergence of a new study—biological therapy or bioregulator therapy based on the development of medical molecular biology, molecular immunity, oncology and cytokine.

The basic characteristics of scientifically grounded modern biological therapeutics are: the preparations used in biological therapy are self substances in the organism, its radical differences from radiotherapy and chemical therapy lie in: it has no progressive damage on normal tissues and cells of the organism, especially immune structure and function, but has regulatory and enhancing effect.

As a non-selective damage therapy, it injures normal histiocyte of the organism while damaging cancer tissue, and tend to cause serous consequences due to serious damage on marrow hematopiesis system and immune structure and function.

With the rapid development of biological technology in medical field, coupled with further understanding of tumor pathogenesis on cellular element level, tumor treatment has entered a new era, shifting from the ear of cell toxicant treatment to the era of targeting treatment.

In light of the overall strategy, tumor treatment is designed to eliminate the tumor cells below a particular order of magnitude by various methods (it is reported that this order of magnitude is 10⁶ for mice, 3.5x10⁹ for human cells, approximately equivalent to globular node with the diameter of 1.5cm), re-motivate, reactivate and recover immunological functions of human body itself under the condition, fulfilling the purpose of long-term peaceful coexistence with tumor, which is the tumor treatment in the 21st century.

The method of thymus removal: take one Kunming white rat aged 8-10 weeks, 21±2g, no matter it is female or male, incise the skin at the breast, cut off 2nd, 3rd and 4th rib, separate them slightly to expose the thymus to quickly remove it and then close the chest cavity rapidly.

Establishment of cancer-bearing animal model: take the fresh tumor from the tumor-bearing rat to make the unicell suspending liquid, after dyeing the cancer cells with lichenin and counting (1x10⁶/ml), make the hypodermic inoculation at the left side of each rat with 0.2ml physiological saline for cancer cells.

Through transplantation in 5th days after thymus removal, the node as large as a soybean came out after 5-6 days and the tumor as large as a finger came out after 10-21 days, the transplanted cancer could survive for 3-4 weeks, however, the passage failed.

Experiment 3: in studying the relation between the metastasis of cancer and the immune, this lab establishes 60 animal models for liver metastatic carcinoma, which are divided into two groups including Group A applied with immune depressant and Group B not applied with immune depressant.

We discuss the atrophy of the thymus of the immune organ in preventing the advance of tumor, seek for the method to recover the functions of the thymus and reconstruct the immune, carry out the cell transplantation of foetal liver, spleen and thymus with the mice and establish the immunologic function through adoptive immunity.

It is shown by the results: through the joint transplantation of three groups of cells, namely S, T and L (200 experimental mice), the entire extinction rate of the tumor in the long term is 46.67% and the one with the entire extinction of the tumor get a long survival life.

then we tried to seek for the drugs for prevention of the formation of the tumor blood vessel from the natural herbs, observed the formation process of the regenerative blood vessel with Olympus micro-circle microscope photograph system and counted the flow rate and flow of the arteriole and venule, found Common Threewingnut Root acetic ether extract (TG) from the traditional Chinese herbs and carried out the blood vessel inhibition test.

Experiment 9: we also found from a large batch of tumor-bearing animal models in the lab that the more the hypodermically inoculated solid tumor of some cancer-bearing experimental mice, the more different the cancer cells of the central tissue of the transplanted solid tumor from the peripheral cancer cells.

DeepMind

or a neural network that may be able to access an external memory like a conventional Turing machine, resulting in a computer that mimics the short-term memory of the human brain.[9][10]

The company made headlines in 2016 after its AlphaGo program beat a human professional Go player Lee Sedol, the world champion, in a five-game match, which was the subject of a documentary film.[11]

A more general program, AlphaZero, beat the most powerful programs playing go, chess and shogi (Japanese chess) after a few days of play against itself using reinforcement learning.[12]

During one of the interviews, Demis Hassabis said that the start-up began working on artificial intelligence technology by teaching it how to play old games from the seventies and eighties, which are relatively primitive compared to the ones that are available today.

DeepMind has opened a new unit called DeepMind Ethics and Society and focused on the ethical and societal questions raised by artificial intelligence featuring prominent philosopher Nick Bostrom as advisor.[33]

In 2017 DeepMind released GridWorld, an open-source testbed for evaluating whether an algorithm learns to disable its kill switch or otherwise exhibits certain undesirable behaviours.[42][43]

To date, the company has published research on computer systems that are able to play games, and developing these systems, ranging from strategy games such as Go[44]

According to Shane Legg, human-level machine intelligence can be achieved 'when a machine can learn to play a really wide range of games from perceptual stream input and output, and transfer understanding across games[...].'[45]

Hassabis has mentioned the popular e-sport game StarCraft as a possible future challenge, since it requires a high level of strategic thinking and handling imperfect information.[46]

As opposed to other AIs, such as IBM's Deep Blue or Watson, which were developed for a pre-defined purpose and only function within its scope, DeepMind claims that its system is not pre-programmed: it learns from experience, using only raw pixels as data input.

Without altering the code, the AI begins to understand how to play the game, and after some time plays, for a few games (most notably Breakout), a more efficient game than any human ever could.[50]

In October 2015, a computer Go program called AlphaGo, developed by DeepMind, beat the European Go champion Fan Hui, a 2 dan (out of 9 dan possible) professional, five to zero.[52]

Go is considered much more difficult for computers to win compared to other games like chess, due to the much larger number of possibilities, making it prohibitively difficult for traditional AI methods such as brute-force.[52][54]

After training these networks employed a lookahead Monte Carlo tree search (MCTS), using the policy network to identify candidate high-probability moves, while the value network (in conjunction with Monte Carlo rollouts using a fast rollout policy) evaluated tree positions.[60]

It won 10 consecutive matches against two professional players, although it had the unfair advantage of being able to see the entire field, unlike a human player who has to move the camera manually.

In October 2019, AlphaStar reached Grandmaster level on the StarCraft II ladder on all three StarCraft races, becoming the first AI to reach the top league of a widely popular esport without any game restrictions.[71]

DeepMind has also collaborated with the Android team at Google for the creation of two new features which will be available to people with devices running Android Pie, the ninth installment of Google's mobile operating system.

It is the first time DeepMind has used these techniques on such a small scale, with typical machine learning applications requiring orders of magnitude more computing power.[73]

In August 2016, a research programme with University College London Hospital was announced with the aim of developing an algorithm that can automatically differentiate between healthy and cancerous tissues in head and neck areas.[75]

Staff at the Royal Free Hospital were reported as saying in December 2017 that access to patient data through the app had saved a ‘huge amount of time’ and made a ‘phenomenal’ difference to the management of patients with acute kidney injury.

Additionally, in February 2018, DeepMind announced it was working with the U.S. Department of Veterans Affairs in an attempt to use machine learning to predict the onset of acute kidney injury in patients, and also more broadly the general deterioration of patients during a hospital stay so that doctors and nurses can more quickly treat patients in need.[79]

Privacy advocates said the announcement betrayed patient trust and appeared to contradict previous statements by DeepMind that patient data would not be connected to Google accounts or services.[82][83]

This included personal details such as whether patients had been diagnosed with HIV, suffered from depression or had ever undergone an abortion in order to conduct research to seek better outcomes in various health conditions.[85][86]

This new subdivision of DeepMind is a completely separate unit from the partnership of leading companies using AI, academia, civil society organizations and nonprofits of the name Partnership on Artificial Intelligence to Benefit People and Society of which DeepMind is also a part.[93]

Google's artificial intelligence system can beat doctors at detecting breast cancer

Google's artificial intelligence system can beat doctors at detecting breast cancer.

Philips and PathAI to improve breast cancer diagnosis with artificial intelligence

Philips and PathAI team up to improve breast cancer diagnosis using artificial intelligence technology in 'big data' pathology research. Royal Philips, a global ...

Deep Learning Algorithms for Detection of Lymph Node Metastases From Breast Cancer

A new study in JAMA reports on how accurate computer algorithms were at detecting the spread of cancer to lymph nodes in women with breast cancer ...

Google AI system beats doctors in detection tests for breast cancer

Title: Google AI system beats doctors in detection tests for breast cancer. || Godhuli News BD Image Credit to “Getty Images, EPA, PA Media, REUTERS/Akhtar ...

MD vs. Machine: Artificial intelligence in health care

Recent advances in artificial intelligence and machine learning are changing the way doctors practice medicine. Can medical data actually improve health care?

2. The Advent of AI in Healthcare

Once thought as a futuristic threat to humankind, artificial intelligence is now a part of everyday life. In healthcare, AI is changing the game with its applications in ...

Google Created Algorithm To Diagnose Breast Cancer

This video was produced by YT Wochit .

AI model improves breast cancer detection on mammograms

A new Artificial Intelligence (AI) model predicts breast cancer in mammograms more accurately than radiologists, reducing false positives and false negatives, ...

Google’s AI system can beat doctors at detecting breast cancer

A Google artificial intelligence system did a better job to detect breast cancer than human doctors assessing images from mammograms, according to a new ...

Google AI could increase detection of breast cancer

New technology developed by a Google software engineer could pave the way for artificial intelligence to help doctors better detect cancer.