跳到正文
原文
Hacker News· sungam·· 3 小时前精选AI 评分69

10 年历史的 Inception v3 CNN 在皮肤癌诊断中胜过 GPT-6 Astra 和 Claude Fable 5.1

A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis

AI 导读

Inception v3 CNN 在 MILK10k 数据集的 200 个活检确认病变上首选诊断正确 125 个(62%),高于 GPT-6 Astra 和 Claude Fable 5.1 的 42%。

推荐理由

统一病例、图像和诊断选项后,专用 CNN 与两个前沿 LLM 的表现可直接对照,文章还公开了病例、提示词和评分代码。

正文 · AI 翻译

译文尚不完整,完整内容请切换到原文。

I am a dermatologist. I tested the ability of GPT-6 Astra and Claude Fable 5.1 to diagnosis skin cancer and found that they were less accurate than I expected. I compared to a 10-year old CNN and to my surprise found that this was superior.

This is a melanoma.

Clinical photograph: Invasive melanoma on the ear, under 0.8 mm thick.Dermoscopic image: Invasive melanoma on the ear, under 0.8 mm thick.

Figure 1. Invasive melanoma on the ear, under 0.8 mm thick. Both LLMs called it a seborrhoeic keratosis and said it could be discharged. The CNN called it a melanoma. Clinical photograph on the left, dermoscopic image on the right. Images: MILK10k, MILK study team, CC BY-NC.

I showed these two images - a clinical photograph and a dermoscopic (skin microscope) image - to GPT-6 Astra and Claude Fable 5.1, two of the most capable AI models available in October 2026. Both said it was a seborrhoeic keratosis, a harmless warty growth, and that the patient could be discharged. I then showed them to fine-tuned version of Inception v3, a convolutional neural network (CNN) first published by Google in 2015 and fine-tuned here on public dermatology images. The CNN got the right answer based on the dermoscopy view.

It was one of 200 biopsy-proven lesions I gave to all three. The CNN named the right diagnosis (out of 6 possiblities) for 125 of them (62%). The two frontier LLMs named it for 84 and 85 (42%). A ten-year-old network, fine-tuned for about twenty minutes, beat both of them at recognising skin cancer.

The test#

The lesions come from MILK10k, a public dataset released through the International Skin Imaging Collaboration in 2025, in which each lesion is photographed twice: a clinical close-up and a dermoscopic image taken through the illuminated magnifying lens dermatologists use. I drew 200 lesions at random, all confirmed by histopathology:

  • 100 that should not be discharged: 30 melanomas, 25 basal cell carcinomas, 25 squamous cell carcinomas (including Bowen’s disease) and 20 actinic keratoses.
  • 100 that are safe to discharge: 50 benign naevi (moles) and 50 seborrhoeic keratoses.

Every lesion was biopsied, including the benign ones, so these are harder to diagnose: a mole that somebody decided to cut out is one that worried a clinician.

Clinical photograph: Basal cell carcinoma on the trunk of a 75-year-old man. Both models answered correctly.Dermoscopic image: Basal cell carcinoma on the trunk of a 75-year-old man. Both models answered correctly.

Basal cell carcinoma on the trunk of a 75-year-old man. All three models answered correctly.

Clinical photograph: Invasive melanoma under 0.8 mm thick, with very little pigment. GPT-6 Astra called it a basal cell carcinoma with 95% confidence.Dermoscopic image: Invasive melanoma under 0.8 mm thick, with very little pigment. GPT-6 Astra called it a basal cell carcinoma with 95% confidence.

Invasive melanoma under 0.8 mm thick, with very little pigment. GPT-6 Astra called it a basal cell carcinoma with 95% confidence. Claude Fable 5.1 and the CNN called it a melanoma.

Clinical photograph: Seborrhoeic keratosis on the leg. Both models called it an actinic keratosis and said it should not be discharged.Dermoscopic image: Seborrhoeic keratosis on the leg. Both models called it an actinic keratosis and said it should not be discharged.

Seborrhoeic keratosis on the leg. Both LLMs called it an actinic keratosis and the CNN a squamous cell carcinoma: all three were wrong, though all three would have kept it rather than discharge it.

Figure 2. Three more of the 200 test lesions. Clinical photograph on the left, dermoscopic image on the right. Images: MILK10k, MILK study team, CC BY-NC.

The LLMs were given both images and nothing else, and asked, as a clinician might use them, for the most likely of the six diagnoses (or “unsure”), a confidence, a second choice, and whether the lesion could be safely discharged with no treatment, biopsy or follow-up. Both models got the same prompt at default settings, and neither refused a case.

该 CNN刻意没有采用最先进的技术。我使用了在日常照片上预训练的 Inception v3,随后在来自 ISIC Archive 的 68,011 张皮肤镜图像和临床图像上,用单块 H100 GPU 微调了所有层。这 200 个测试病灶,以及同一病灶或患者的其他所有照片,均在训练前从其数据中移除(包括验证集),因此模型从未见过它们;它们也没有被用于选择模型或设定阈值。它对每个病灶的两张图像分别评分,再将两者合并,其中皮肤镜图像占大部分权重,最后从同样的六种诊断中选择。

你可以亲自试用这个 CNN。出人意料的是,这个模型足够小,完全可以在手机浏览器中通过 WebGPU 运行。不会上传任何内容,其随机抽样按钮会从上述同样的 200 个病灶中抽取。

诊断:62% 对 42%#

图 3。两个 LLM 和 CNN 的首选诊断正确情况;CNN 同样从六种诊断中选择。标签显示答对数量,分母为具有该组织学类型的病灶数。

总体而言以及在大多数诊断上,CNN 答对的次数更多。允许选择第二诊断后,它答对 200 个中的 173 个,另外两个模型分别为 134 个和 138 个。它正确识别了 30 个黑色素瘤中的 13 个,另外两个模型分别为 8 个和 11 个。差距最大的是无害病灶:它正确识别出 50 个痣中的 37 个和 50 个脂溢性角化病中的 26 个;GPT-6 Astra 分别为 16 个和 13 个,Claude Fable 5.1 分别为 33 个和 6 个。在基底细胞癌方面,它比 GPT-6 Astra 少答对一个;在日光性角化病方面,它落后于两个 LLM。

这些模型的失败方式各不相同。每个 LLM 都有一种偏爱的答案:GPT-6 Astra 将 75 个病灶误判为基底细胞癌,而实际只有 25 个,其中包括 30 个黑色素瘤中的 14 个;Claude Fable 5.1 将 53 个病灶误判为日光性角化病,而实际只有 20 个。CNN 对黑色素瘤的误判则恰好相反:在它误诊的 17 个黑色素瘤中,有 8 个被判为痣,6 个被判为脂溢性角化病。

结果汇总于一张表中#

GPT-6 Astra Claude Fable 5.1 CNN (Inception v3)
诊断正确数(共 200 个) 84 (42%) 85 (42%) 125 (62%)
首选或第二选择正确 134 138 173
首选为黑色素瘤(共 30 个) 8 11 13
保留的不安全病灶(共 100 个) 97 96 按其预设阈值保留 77 个;匹配后为 98 个或 99 个
放行的安全病灶(共 100 个) 32 22 按其预设阈值放行 76 个
放行的黑色素瘤(共 30 个) 3 4 按其预设阈值放行 18 个;匹配后为 2 个或 1 个

注意事项#

  • 样本量小。200 个病灶足以显示这一模式,但不足以对接近的结果进行排名;而 30 个黑色素瘤也让最重要的指标存在很大的不确定性。各 LLM 病例均仅运行一次;不同运行之间的答案会有所差异。
  • 困难病例。所有病灶均接受了活检。在存档库的普通图像上,CNN 对应放行与不应放行的病灶区分得好得多(ROC 曲线下面积为 0.96,而这里为 0.86)。
  • 数据污染。MILK10k 自 2025 年起就已公开,因此 LLM 在训练中可能见过它;如果有什么影响,那也只会帮助它们。CNN 则肯定没有见过它。
  • 并非最先进技术。Inception v3 只是一个基线。最先进的皮肤癌诊断 AI 使用在更多数据上训练的图像 Transformer 集成;基于这些模型构建的受监管产品表现要好得多。

作为患者提问#

改为以患者身份提问,仅提供临床照片并询问“我需要去看医生吗?”,两个 LLM 几乎在所有病例中都建议去看医生,包括无害病灶:对于另外 100 个经活检证实的黑色素瘤,它们分别有 99 个和 98 个建议就医。

结论#

一个小型、陈旧且专用的网络,在识别皮肤病变方面远胜于两款前沿 LLM。

亲自运行#

病例、提示词、每一条 LLM 回复以及评分代码都集中在一个下载包中,CNN 则在这里。

我设计了这个测试,并作出了临床判定。分析和初稿使用 Claude Code(Anthropic 的编程工具)完成,该工具运行在 Claude 模型上;接受测试的两款 LLM 中也有一款来自 Anthropic。评分由脚本对照组织学检查结果完成。

图片来自 MILK10k 数据集(MILK 研究团队、International Skin Imaging Collaboration),依据 CC BY-NC 许可使用。

Dr Magnus Lynch 是 Guy's Hospital 的顾问皮肤科医生和莫氏外科医生,也是 King's College London 的荣誉讲师(相当于副教授)。他的临床工作涵盖皮肤癌、莫氏手术和面部重建手术以及激光治疗;他的研究涵盖皮肤癌和瘢痕的细胞生物学,以及人工智能在皮肤科中的应用。 完整个人简介。

来源:Hacker News · lynchlab.net