Deep learning for pancreatic cancer detection: current challenges and future strategies

Abstract

In The Lancet Digital Health, Kao-Lang Liu and colleagues 1 describe the applications of a convolutional neural network (CNN) in distinguishing CT images of pancreatic cancer tissue from non-cancerous pancreatic tissue. 1 Contrast-enhanced CT images of 370 patients with pancreatic cancer and 320 controls from a Taiwanese centre were manually segmented and CNN was trained to classify image patches as cancerous or noncancerous. Performance of CNN was compared with radiology reports in the local test sets. Similar to results from previous studies on this topic, 2,3 CNN achieved a remarkable performance, with accuracy of 0•986-0•989 in the local test dataset. CNN achieved higher sensitivity than that of radiologists in the local test sets (0•983 vs 0•929; p=0•014). The three tumours that were missed by the CNN were 1•1-1•2 cm in size, of which two were correctly classified by radiologists. Impressively, CNN was able to correctly classify 11 of the 12 tumours that were missed by radiologists, which were 1•0-3•3 cm in size. 1 These promising results show that CNN as a second reader can reduce misdiagnosis of pancreatic cancer and possibly lead to improved patient outcomes.Whereas previous publications relied on data from a single institution, 2, 3 Liu and colleagues also externally validated data with publicly available datasets from the USA, with an accuracy of 0•832. Importantly, external datasets of individuals with normal pancreas and pancreatic cancer patients originated from different sources: 82 patients with healthy pancreas from the Cancer Imaging Archive dataset and 281 patients with pancreatic cancer from the Medical Segmentation Decathlon dataset from Memorial Sloan Kettering Cancer Center, New York, NY, USA. Ideally, all patients from the external data should be from the same institution to ensure that the classification task is not affected by technical differences between the two institutions. The authors showed that a significant positive correlation existed between tumour size and CNN performance on both the internal and external datasets, which suggested that the CNN detected actual differences in pancreatic imaging features, rather than technical differences.These preliminary experiences in applying a CNN to detect pancreatic cancer show tremendous promise, but

Physical distancing and the perception of interpersonal distance in the COVID-19 crisis

“…The virus is transmitted by aerosols and droplet particles, predominantly during face-to-face social interactions 1 . Mandatory measures to combat the spread of the virus include wearing a face mask and maintaining a minimum interpersonal distance (IPD) of at least 1.5 m to 2 m 2 – 4 . Note, however, that distance requirements vary substantially between countries (e.g., France: 1.0 m; South Africa: 1.5 m; the USA: 1.8 m; Japan: 2.0 m).…”

“…Note, however, that distance requirements vary substantially between countries (e.g., France: 1.0 m; South Africa: 1.5 m; the USA: 1.8 m; Japan: 2.0 m). This should reduce the reproduction rate of the pandemic respiratory virus by around 38 percent 5 and has so far proven its effectiveness 4 . However, we usually prefer an IPD of around 1 m when interacting with unfamiliar people 6 , 7 .…”

Pancreatic cancer grading in pathological images using deep learning convolutional neural networks

“…Convolutional neural network (CNN) is a widely used deep learning (DL) algorithm in medical image-based classification and prediction. 8 Several methods use CNN in cancer detection and diagnosis 9 such as the Gleason grading of prostate cancer, [10][11][12] colon cancer grading, 13 breast cancer detection, 14,15 and pancreatic cancer detection [16][17][18][19] and classification. 20 AI has been proven to assist clinicians with better prediction and faster diagnosis for breast cancer screening.…”

Pancreatic cancer grading in pathological images using deep learning convolutional neural networks

“…Convolutional neural network (CNN) is a widely used deep learning (DL) algorithm in medical image-based classification and prediction. 7 Several methods use CNN in cancer detection and diagnosis 8 such as the Gleason grading of prostate cancer, [9][10][11] colon cancer grading, 12 breast cancer detection, 13,14 and pancreatic cancer detection [15][16][17][18] and classification. 19 However, grading of pancreatic cancer with DL still needs comprehensive study.…”