NEWS AI improves pathologists’ performance
Pathologists’ examinations of tissue samples from skin cancer tumours improved when they were assisted by an AI tool. The assessments became more consistent and patients’ prognoses were described more accurately, details a new study. The paper, published recently in JAMA Network Open, reports the results of a study led by Karolinska Institutet, conducted in collaboration with researchers from Yale University. Tumour-infiltrating lymphocytes (TILs)
are an important biomarker in several cancers, including malignant melanoma, their presence plays a role in both diagnosis and prognosis, with a high presence being favourable. An important part of pathologists’ work in malignant melanoma is
BD’s diagnostic business to combine with Waters
Waters Corporation and Becton Dickinson (BD) have announced a definitive agreement to combine BD’s Biosciences & Diagnostic Solutions business with Waters, creating an innovative life science and diagnostics leader with pioneering technologies. US-based Waters is a global leader in analytical instruments, separations technologies, and software, serving the life, materials, food, and environmental sciences for over 65 years. The deal creates a combined company with expected 2025 sales of approximately $6.5 billion and adjusted EBITDA of approximately $2.0 billion. It is described by the two firms as a strong strategic fit that increases presence in multiple high-growth areas. The agreement is structured as a tax-efficient Reverse Morris Trust transaction valued at approximately $17.5 billion. The newly created company will bring together complementary technologies to serve high-volume testing in regulated end-markets including liquid chromatography, mass spectrometry, flow cytometry, and diagnostic solutions. BD’s regulatory expertise and established presence in clinical and diagnostic settings is expected to drive enhanced market access, improved service support, accelerated menu expansion, and automation for multiplex diagnostics using LC-MS technologies from Waters.
WWW.PATHOLOGYINPRACTICE.COM AUGUST 2025 11
tissue sections and estimating the amount of TILs according to current guidelines. The second group included pathologists,
to estimate the number of TILs. Researchers at Karolinska Institutet in Stockhom, Sweden, have now investigated how pathological assessments were affected by an AI tool trained to quantify TILs.
The study included 98 pathologists and
researchers from other professions divided into two groups. One group consisted solely of experienced pathologists. They worked as usual by looking at digital images of stained
but also researchers from other professions – all of whom had some experience in assessing pathological images. They also looked at the images as usual, but were assisted by AI support that quantified the number of TILs. All assessed 60 sections from patients with malignant melanoma. The assessments made with AI support
were superior to the others in several ways. Among other things, reproducibility was very high – the results were very similar regardless of who performed the review. The AI-supported assessments also provided a more accurate picture of the patients’ disease prognoses.
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72
