AJ Watson

PACS/VNA
The cloud for healthcare providers: One size does not fit all
In a new column, AJ Watson of Intelerad Medical Systems discusses the merits of a hybrid approach to cloud computing for medical image management.
July 23, 2023
2020 01 28 20 45 5229 Cloud Computing Laptop 400
AI
What's next for AI regulations in medical imaging?
The U.S. Food and Drug Administration continues to consider its approach to regulating artificial intelligence (AI) software. AJ Watson of Intelerad Medical Systems makes the case for flexible and adaptable regulation of the technology.
September 26, 2022
2019 12 09 17 23 6730 Artificial Intelligence Ai Suit 400
Page 1 of 1
Top Stories
Breast Mammo Computer 400 (3)
AI
AI tools may not meet breast radiologists' expectations in practice
AI tools in breast imaging may have more modest clinical impact on recall and biopsy rates.
Lung Cancer
CT
Stepped reminders boost CT lung cancer screening
Example cases illustrate the double-edged role of large language model (LLM) rationale quality. (A) A 50-year-old female patient with a palpable anterior chest wall mass (correct diagnosis: solitary fibrous tumor of the pleura). The LLM incorrectly suggested synovial sarcoma but provided a persuasive rationale (quality score: 4 of 5), describing a well-defined nodule at axial contrast-enhanced CT spanning the pleura and intercostal space with heterogeneous strong enhancement. Four of five readers (80%) accepted the incorrect suggestion. FDG = fluorodeoxyglucose. (B) A 61-year-old male patient with diabetes presented with cough, sputum, and dyspnea (correct diagnosis: mucormycosis). The LLM correctly suggested mucormycosis with an excellent rationale (quality score: 5 of 5), integrating the reverse halo sign on serial axial CT images and rapidly progressive cavitary lesions. Three of five readers initially selected incorrect diagnoses; after LLM output, all five selected the correct diagnosis (100% acceptance). Blue and orange reader icons denote high- and low-expertise readers, respectively.
AI
Model confidence, reader expertise affect reader-LLM collaboration
Ga-68 HER2-PET/CT images before neoadjuvant therapy, at end of second cycle, and before surgery. (A) Baseline scan demonstrated soft-tissue lesion measuring approximately 2.3 × 2.2 cm in upper outer quadrant of left breast, with marked radiotracer uptake and SUVmax of 10.1. (B) At end of second cycle, imaging revealed residual lesion of approximately 2.2 × 1.0 cm in same region, without abnormal radiotracer accumulation. (C) Preoperative imaging demonstrated further reduction in lesion size to approximately 2.0 × 0.6 cm, with no abnormal tracer uptake detected.
Molecular Imaging
PET/CT predicts response to neoadjuvant therapy in breast cancer
Nominations Are Open — 2026 Minnies
Sponsor Content
Nominations Are Open — 2026 Minnies
More in Home
AI tools may not meet breast radiologists' expectations in practice
By Amerigo Allegretto
AI tools in breast imaging may have more modest clinical impact on recall and biopsy rates.
August 12, 2026
Breast Mammo Computer 400 (3)
Stepped reminders boost CT lung cancer screening
By Will Morton
Trial findings directly address the current lack of effective lung cancer screening interventions.
August 11, 2026
Lung Cancer
Model confidence, reader expertise affect reader-LLM collaboration
By Amerigo Allegretto
Successful human-LLM collaboration is associated with model confidence and reader expertise in chest imaging.
August 11, 2026
Example cases illustrate the double-edged role of large language model (LLM) rationale quality. (A) A 50-year-old female patient with a palpable anterior chest wall mass (correct diagnosis: solitary fibrous tumor of the pleura). The LLM incorrectly suggested synovial sarcoma but provided a persuasive rationale (quality score: 4 of 5), describing a well-defined nodule at axial contrast-enhanced CT spanning the pleura and intercostal space with heterogeneous strong enhancement. Four of five readers (80%) accepted the incorrect suggestion. FDG = fluorodeoxyglucose. (B) A 61-year-old male patient with diabetes presented with cough, sputum, and dyspnea (correct diagnosis: mucormycosis). The LLM correctly suggested mucormycosis with an excellent rationale (quality score: 5 of 5), integrating the reverse halo sign on serial axial CT images and rapidly progressive cavitary lesions. Three of five readers initially selected incorrect diagnoses; after LLM output, all five selected the correct diagnosis (100% acceptance). Blue and orange reader icons denote high- and low-expertise readers, respectively.
PET/CT predicts response to neoadjuvant therapy in breast cancer
By Will Morton
Monitoring neoadjuvant therapy response in HER2-positive breast cancer is challenging with existing tools.
August 11, 2026
Ga-68 HER2-PET/CT images before neoadjuvant therapy, at end of second cycle, and before surgery. (A) Baseline scan demonstrated soft-tissue lesion measuring approximately 2.3 × 2.2 cm in upper outer quadrant of left breast, with marked radiotracer uptake and SUVmax of 10.1. (B) At end of second cycle, imaging revealed residual lesion of approximately 2.2 × 1.0 cm in same region, without abnormal radiotracer accumulation. (C) Preoperative imaging demonstrated further reduction in lesion size to approximately 2.0 × 0.6 cm, with no abnormal tracer uptake detected.
5 factors that led to California workplace MRI accident
By Liz Carey
What happened at a Redwood City hospital in California in 2023.
August 11, 2026
The Invisible Force Podcast Album Cover Auntminnie Jan 2026 Thumbnails
NME breast lesions have high malignancy rate on MRI-guided biopsy
By Amerigo Allegretto
Biopsies from women with a known ipsilateral malignancy have a higher frequency of breast cancer.
August 10, 2026
Mri Breast 400
Many women interested in AI-based risk assessment for breast cancer
By Amerigo Allegretto
Survey findings also show that most women at higher risk are interested in additional screening tests.
August 10, 2026
Breast Cancer 400
CT 5-star quality rating system supports optimization
By Will Morton
The rating framework demonstrated robust reproducibility, with three-reader concordance reaching up to 93% in highly standardized centers.
August 7, 2026
Radiation Symbol
READ-DVT model performs well in finding DVT from ultrasound reports
By Amerigo Allegretto
The AI model accurately identified the presence or absence of deep vein thrombosis on unstructured ultrasound reports.
August 7, 2026
Radiological Report 400
Bone scan testing has fallen 35% among Medicare beneficiaries
By Will Morton
Declines in testing were greatest among certain underserved groups.
August 7, 2026
Dexa
MRI-based models may predict atypical brain development in children
By Amerigo Allegretto
The models could provide a framework for identifying which adolescents are at higher risk of developing psychiatric conditions.
August 7, 2026
Child Girl Stuffed Animal 400
Ultrasound MinnieCast, Episode 14: Weathering the sonographer shortage
By Amerigo Allegretto
SDMS President Aubrey Rybyinski discusses how clinics can address sonographer vacancies.
August 7, 2026
Minnie Cast Thumbnail (18)
Page 1 of 243
Next Page