1月1日《自然》雜志發(fā)布的一項最新研究顯示，人工智能從常規(guī)乳房X線掃描中識別乳腺癌的得分已經(jīng)超過了醫(yī)學專家。
乳腺癌是女性最高發(fā)的癌癥之一。對于女性而言，定期做一次乳房X光檢查是很有必要的。但掃描結果解讀不可避免會存在一定誤差。為此，谷歌一種人工智能模型出現(xiàn)了！這個模型可以根據(jù)掃描結果預測乳腺癌，其準確性與放射科專家相似。
然而一旦涉及到人工智能，類似的顧慮就會被提及：人工智能是否最終會取代人？
圖片來源：視覺中國
A computer programme can identify breast cancer from routine scans with greater accuracy than human experts, researchers said in what they hoped could prove a breakthrough in the fight against the global killer.
研究人員稱，一種電腦程序可以通過常規(guī)掃描準確識別乳腺癌，而且它的準確率比人類專家的更高。他們希望該電腦程序可以在與乳腺癌這一全球殺手的斗爭中取得突破。
Breast cancer is one of the most common cancers in women, with more than 2 million new diagnoses last year alone.
乳腺癌是女性最常罹患的癌癥之一，僅去年一年就有200多萬名新確診的病例。
Regular screening is vital in detecting the earliest signs of the disease in patients who show no obvious symptoms.
在患者沒有明顯癥狀的時候，定期篩查對于發(fā)現(xiàn)疾病的早期癥狀至關重要。
In Britain, women over 50 are advised to get a mammogram every three years, the results of which are analysed by two independent experts.
在英國，50歲以上的婦女被建議每三年做一次乳房X光檢查，而其檢查結果由兩位單獨的專家進行分析。
But interpreting the scans leaves room for error, and a small percentage of all mammograms either return a false positive - misdiagnosing a healthy patient as having cancer - or false negative - missing the disease as it spreads.
但對掃描結果的解讀也有可能出錯，而且在所有乳房X光檢查結果中，有一小部分要么是假陽性（將健康病人誤診為患有癌癥），要么是假陰性（在疾病的傳播過程中，沒有診斷出疾病）。
Now researchers at Google Health have trained an artificial intelligence model to detect cancer in breast scans from thousands of women in Britain and the United States.
如今谷歌健康中心的研究人員已訓練出一個人工智能模型，它可以通過乳房掃描來檢測英國和美國數(shù)千名女性是否罹患癌癥。
The images had already been reviewed by doctors in real life but unlike in a clinical setting, the machine had no patient history to inform its diagnoses.
實際上，醫(yī)生們已經(jīng)檢查過這些圖像了，不過與臨床環(huán)境不同的是，這臺機器不知道病人的病史，也沒有據(jù)此來進行診斷。
The team found that their AI model could predict breast cancer from the scans with a similar accuracy level to expert radiographers.
該研究團隊發(fā)現(xiàn)，他們的人工智能模型可以通過掃描檢查來預測乳腺癌，而且其準確度與放射科專家相當。
Further, the AI showed a reduction in the proportion of cases where cancer was incorrectly identified - 5.7 percent in the US and 1.2 percent in Britain, respectively.
此外，該人工智能模型還顯示，癌癥被錯誤識別的比例有所下降，其中美國降低了5.7%，英國降低了1.2%。
It also reduced the percentage of missed diagnoses by 9.4 percent among US patients and by 2.7 percent in Britain.
美國和英國的漏診率也分別降低了9.4%和2.7%。
"The earlier you identify a breast cancer the better it is for the patient," Dominic King, UK lead at Google Health, told AFP.
“越早發(fā)現(xiàn)乳腺癌，對病人越好，”谷歌健康中心英國分部負責人多米尼克?金告訴法新社。
"We think about this technology in a way that supports and enables an expert, or a patient ultimately, to get the best outcome from whatever diagnostics they've had."
“我們認為這項技術能夠支持并最終使專家或患者從他們得到的診斷中獲得最佳結果?！?/div>
多知道一點
乳腺癌
乳腺是由皮膚、纖維組織、乳腺腺體和脂肪組成的，乳腺癌是發(fā)生在乳腺腺上皮組織的惡性腫瘤。90%以上的乳腺癌發(fā)生在女性身上。
乳腺并不是維持人體生命活動的重要器官，原位乳腺癌并不致命；但由于乳腺癌細胞喪失了正常細胞的特性，細胞之間連接松散，容易脫落。癌細胞一旦脫落，游離的癌細胞可以隨血液或淋巴液播散全身，形成轉移，危及生命。
全球乳腺癌發(fā)病率自20世紀70年代末開始一直呈上升趨勢。目前乳腺癌是女性最高發(fā)的癌癥之一，僅2019年便有超過200萬例新診斷。
?
